Skip to main content
Bring your product to a global audience: synthesize speech with the same voice across a wide range of languages. The Realtime TTS-2 models — inworld-tts-2 and inworld-tts-2-flash — share the same language support. For multilingual applications, inworld-tts-2 is the most capable choice, with the most accurate pronunciation and intonation; inworld-tts-2-flash offers the same language coverage at the lowest latency and cost.

​
Supported languages

The Realtime TTS-2 models support 200+ unique languages and locales (BCP-47 codes) — from broad languages like es (Spanish) to regional locales like es-MX (Mexican Spanish). The languages we actively support and test are listed below.
Timestamp alignment is available in every language the model supports.

​
Generally available languages

These languages are generally available (GA), offering the highest quality and the most natural pronunciation:

​
Experimental languages

These languages are experimental — pronunciation and quality can vary more than for GA languages. To try one, design or clone a voice in that language.
* These are base language subtags (ISO 639-1, or ISO 639-3 for less common languages).
Accents and regional variants: A voice reproduces the specific accent it was cloned in (e.g., a voice cloned in British English speaks en-GB natively). If your voice wasn’t cloned in the accent you need, pass the matching BCP-47 regional code in the language field (e.g., en-GB, es-MX, pt-BR) to steer it. See Specifying a language below.
Text normalization is language-specific, not locale-specific — English is normalized the same way whether you target en-US or en-GB, even though conventions for dates, currencies, and the like can differ. If you need locale-specific formatting, normalize that text yourself.

​
Cross-lingual support

A voice delivers the best speaker similarity when it speaks the language it was cloned in — its native tongue. The Realtime TTS-2 models support cross-lingual synthesis. When synthesizing a different language, the model makes a best-effort attempt to speak the target language natively, without carrying over the accent of the voice’s original language. If you want the voice to keep its original accent, prompt for it explicitly (e.g., with steering on inworld-tts-2). For the most natural, consistent cross-lingual results, we recommend specifying the language to synthesize in and localizing the voice.

​
Specifying a language

Use the language field to tell the model which language (as specified by a BCP-47 language tag) the voice should speak the text in. When set, the service will:
  • Apply text normalization (if enabled) for the target language (e.g., speaking numbers in the target language).
  • Use the voice’s localized prompt for that language, if one exists. If no localized prompt is available, the model will be steered to speak in the target language.
When language is omitted, the original voice prompt is used and the language for normalization (if enabled) is auto-detected from the input text. If you are sending short requests with only numbers or dates (e.g., 123-456-7890), auto-detection may not have enough context to detect the right language. In those cases, we recommend specifying a language for most consistent results.
A voice’s native (prompt) language shapes how it sounds in other languages — speaker similarity is always highest in the voice’s native tongue. For accent-free, native delivery in another language, localize the voice.

​
Voice localization

Voice localization adapts a voice to a target language so it sounds like a native speaker of that language — delivering fluent, natural speech without carrying over the accent of the voice’s original language. (By contrast, specifying a language on an un-localized voice may retain the original accent.) It is supported for all Inworld TTS models.
1

Open the Voices page in Portal

In Inworld Portal, go to Voices and select the My voices tab. Hover over an English voice to open its details panel on the right.
Voice localization is currently only supported for voices where the original audio was in English. Support for additional languages is coming soon.
2

Click Localize Voice

With a voice selected, click Localize Voice in the right panel.Voices page with Localize Voice action
3

Choose a target language

Pick a target language from the dropdown and click Localize, which will start generating localized prompt candidates. This may take up to 2 minutes.Localize Voice screen with target language dropdown
4

Review candidates

After generation, you’ll see a few localized prompt candidates. Listen to each and pick the one that sounds most natural and native, then click Save.If none sound right, you can click Regenerate. You may want to change the script before regenerating, since the script influences the generated voice.Review candidates screen with multiple localized voice options
5

Use the localized voice

Once saved, the voice will use your localized prompt when you specify the language to match the language of your localized prompt. Try it out in TTS Playground or via API (the voice ID remains the same).TTS Playground generating speech with a localized voice

​
Next steps

Voice Cloning

Clone a voice once and reuse it across languages.

Custom Pronunciation

Use IPA notation to control pronunciation of proper nouns and edge cases.